Add Mem0 integration - support for Mem0 platform

[Amnah199]

Related Issues

• partially fixes - #219

Proposed Changes:

• This PR integrates mem0 as a memory store in Haystack, supporting basic add, retrieve, and delete operations.
• It updates the memory_agents.Agent class to enable retrieving and persisting long-term conversational context.

Key Changes

• Added memory support to memory_agents.Agent.
• Before each execution, relevant memories are fetched from Mem0MemoryStore using the latest user message as the query.
• Retrieved memories are injected into the conversation as [MEMORY #n] ChatMessage objects.
• When memories exist, the system prompt is updated to tell the LLM that [MEMORY] messages represent long-term context.
• After each run, new user and assistant messages are saved to the memory store.
• Memory is optional; agents behave normally when memory_store=None.

How did you test it?

• Unit and Integration Tests
• Tested locally with examples

Notes for the reviewer

Support for Memory.from_config will be revised in a separate PR as it has a slightly different implementation than mem0 MemoryClient.
https://docs.mem0.ai/platform/platform-vs-oss

Checklist

• I have read the contributors guidelines and the code of conduct
• I have updated the related issue with new insights and changes
• I added unit tests and updated the docstrings
• I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.
• I documented my code
• I ran pre-commit hooks and fixed any issue

[coveralls]

Pull Request Test Coverage Report for Build 21253212844

Details

• 0 of 0 changed or added relevant lines in 0 files are covered.
• 106 unchanged lines in 1 file lost coverage.
• Overall coverage decreased (-3.3%) to 64.843%

---

Files with Coverage Reduction	New Missed Lines	%
components/agents/agent.py	106	53.15%

Totals
Change from base Build 21230795241:	-3.3%
Covered Lines:	972
Relevant Lines:	1499

---

💛 - Coveralls

[sjrl]

@Amnah199 I noticed that the tests are failing for AWS since it's not set up for this repo. I'd check how it's done in our core integrations repo. Also I noticed a lot of tests for Mem0 are being skipped could you see why that's the case?

[sjrl]

Suggested change

	GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
	GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
	AWS_REGION: "us-east-1"

[sjrl]

And right before integration-tests: add this block

      # Do not authenticate on PRs from forks and on PRs created by dependabot
      - name: AWS authentication
        id: aws-auth
        if: github.event_name == 'schedule' || (github.event.pull_request.head.repo.full_name == github.repository && !startsWith(github.event.pull_request.head.ref, 'dependabot/'))
        uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708
        with:
          aws-region: ${{ env.AWS_REGION }}
          role-to-assume: ${{ secrets.AWS_CI_ROLE_ARN }}

[sjrl]

Seems like we also have this in the bedrock integration tests

Suggested change

	- name: Run
	- name: Run
	if: success() && steps.aws-auth.outcome == 'success'

[sjrl]

@anakin87 could we ask for your help on what might be going wrong with the AWS auth setup in tests?

[anakin87]

@sjrl try adding

permissions:
  id-token: write
  contents: read

on the test workflow, on top level
as in https://github.com/deepset-ai/haystack-core-integrations/blob/943ad7f0e7633dd43a0331602ec41c6074fca5c3/.github/workflows/amazon_bedrock.yml#L22-L24

It seems it also worked on this repo in the past

[sjrl]

Thanks for all of the work on this!

Let's make sure to add a pydoc for this in a follow up PR